- 🎨 Custom-configured Stable Diffusion 3.5 build, Venice's default image model.
- 🔒 Privacy-first: prompts and images stored locally, never on servers.
- 🔧 Runs a specialized ComfyUI workflow backend for optimized processing.
- 🆕 Launched within Venice Image Engine V2, March 2025.
- 📏 Accepts pixel-based width and height parameters, for example 1024×1024.
- ⚡ Pairs with a separate upscale-and-enhance system doubling or quadrupling resolution.
- 🌐 OpenAI-compatible API with optional watermark control.
- 🏢 Built on Stability AI's open Stable Diffusion 3.5 architecture.
Stability AI is a UK-based artificial intelligence company best known for creating Stable Diffusion, one of the most widely adopted text-to-image generation models in the AI ecosystem. The company has established itself as a leading force in open-weight generative media, with…
Explore 1 more model by Stability AI →Venice SD35 is Venice's self-hosted, privacy-preserving text-to-image model, built on Stability AI's open-source Stable Diffusion 3.5 architecture. Introduced as the default model in Venice Image Engine V2 in March 2025, it wraps the base SD 3.5 weights in a custom-configured engine powered by a ComfyUI workflow backend. Venice emphasizes that prompts and generated images remain in the user's local browser rather than on company servers, reflecting its privacy-first positioning.
According to Venice's own materials, the team runs a specialized pipeline configured for cleaner, sharper output than an off-the-shelf deployment. The Image Engine V2 release also pairs SD35 with a new upscaling system that doubles or quadruples resolution while preserving the original style and details, a recommended two-step workflow: generate first, then upscale and enhance.
Through the Venice API, the model is addressed by its identifier and accepts pixel-based sizing with width and height, alongside parameters such as step count, negative prompts, style presets, and an option to hide the watermark. The endpoints are OpenAI-compatible.
Venice SD35 sits within a broader Venice generative lineup that includes the adult-oriented image model Lustify SDXL and the audio-generation model Stable Audio 2.5, spanning images, music, and beyond under the same privacy-centric platform.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
| Seller | Reputation↓ | Routing | $ / img | Categories | API |
|---|---|---|---|---|---|
| Venice.ai Proxy 0x1f22…18c9 | 100.00 | #2 | $0.005 | image,creative | openai-images |
| ▲ Apex Ant 0x73b4…e736 | 91.01 | #1 | $0.004 | image,media | openai-images |
| D5V1N2 0xd5e7…7be0 | 33.17 | gated | $0.012 | image,creative,router,fallback | openai-images |
"Best price" and the seller table are live AntSeed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = on-chain trust (0-100). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on AntSeed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.